KR20240043252A - Simulating device and method by digital twin using distributed computing - Google Patents

Abstract

A digital twin simulation method using distributed computing is provided. A digital twin simulation method according to some embodiments of the present invention includes acquiring first physical data including real-time state information of a physical object; generating semantic data representing the state of the physical object based on pre-stored second physical data that is static state information of the physical object and the first physical data; Analyzing the semantic data, partitioning the semantic data into at least one sub-semantic data, and allocating a simulation session corresponding to the sub-semantic data; and performing a simulation of a digital twin for the physical object through the simulation session.

Description

Digital twin simulation device and method using distributed computing {SIMULATING DEVICE AND METHOD BY DIGITAL TWIN USING DISTRIBUTED COMPUTING}

The present invention relates to a digital twin simulation device and method, and more specifically, to assigning a simulation session based on the state information of the physical object that is the subject of simulation, and performing simulation of the physical object by the digital twin using an optimized simulation session. This relates to a digital twin simulation device and method using distributed computing.

Due to the advancement of IT technology, the demand for digital twins that provide simulations for analysis, prediction, and optimization of the state of specific physical objects or systems in a virtual environment is increasing, and the development of corresponding technologies is also continuously advancing.

Digital twin-based simulation has developed to a level where accurate predictions can be made by utilizing formula-based models that simulate the state of physical objects and high-resolution sensor data, but simulation time increases due to the enormous amount of computing resources and the resulting increase in processing time. There is a problem.

To solve this problem, a method is being applied to support a rapid simulation process by dividing the required model into smaller sub-models, assigning each to multiple computing nodes, and processing them simultaneously. However, in the case of such distributed computing, the There is a limit to the latency of having to wait for the node with the longest computing time to terminate for state synchronization.

In order to overcome the above latency problem, a method of dividing the model has been developed considering the number or distribution of computing points where simulation operations occur, but it takes excessive time to predict the computing load (number of points, distribution, etc.). There is a problem in that the overall simulation time actually increases.

Japanese Patent Publication No. 2007-249491 (published on September 27, 2007)

The technical problem to be solved by the present invention is to provide a digital twin simulation device and method that can perform a balanced partitioning operation based on the state information of physical objects and thereby perform rapid and accurate simulation.

In addition, a digital twin simulation that distinguishes between real-time state information and static state information of physical objects and performs efficient distributed computing using semantic data generated based on real-time state information input from physical objects and previously stored static state information. To provide a device and method.

In addition, it provides a digital twin simulation device and method that enables more efficient and rapid simulation processing by determining whether to predict computing load depending on the degree of change in physical objects included in semantic data.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

A simulation method of a digital twin using distributed computing according to some embodiments of the present invention for achieving the above technical problem includes the steps of acquiring first physical data including real-time state information of a physical object; generating semantic data representing the state of the physical object based on the first physical data and pre-stored second physical data, which is static state information of the physical object; Analyzing the semantic data, partitioning the semantic data into at least one sub-semantic data, and allocating a simulation session corresponding to the sub-semantic data; And it may include performing a simulation of a digital twin for the physical object through the simulation session.

According to one embodiment, the step of allocating the simulation session includes determining whether to predict the simulation computing load based on state information of the physical object included in the semantic data, and predicting the simulation computing load when the load prediction is determined. and allocating the simulation session based on a simulation computing load prediction result.

According to one embodiment, the step of determining whether to predict the simulation computing load may include determining whether to predict the simulation computing load by analyzing real-time state information of the first physical data and static state information of the second physical data. .

According to one embodiment, the simulation of the digital twin is a simulation of predicting the spread of a forest fire, and the first physical data includes at least one of the surrounding temperature, humidity, precipitation, wind direction, wind speed, forest fire spread area, and ignition point of the physical object. It includes, wherein the second physical data includes at least one information of the altitude, slope, slope direction, fuel model, and past forest fire state data of the physical object, and the step of determining whether to predict the simulation computing load includes: It may be determined whether to predict the simulation computing load by analyzing the first physical data and the second physical data.

According to one embodiment, the simulation of the digital twin is a manufacturing process simulation, and the first physical data includes at least one information of the operating state, failure status, temperature, and power consumption of the facility, which is the physical object, and 2 The physical data includes at least one information of the manufacturing target of the physical object, the manufacturing process sequence, and the number of equipment inputs, and the step of determining whether to predict the simulation computing load includes the first physical data and the second physical data. It is possible to determine whether to predict the simulation computing load by analyzing .

According to one embodiment, the step of determining whether to predict the simulation computing load includes 1-1 physical data including real-time state information of the physical object at the previous point in time and real-time state information of the physical object at the most recent point in time. It may be determined whether to predict the simulation computing load based on the comparison result of the first and second physical data including.

According to one embodiment, the step of determining whether to predict the simulation computing load includes performing the simulation computing load prediction when the difference between the 1-1 physical data and the 1-2 physical data is greater than or equal to a predefined reference difference. If it is less than the reference difference, it may be decided to allocate the simulation session without performing the simulation computing load prediction.

According to one embodiment, the simulation of the digital twin is a simulation of predicting the spread of a forest fire, and the first physical data includes at least one of the surrounding temperature, humidity, precipitation, wind direction, wind speed, forest fire spread area, and ignition point of the physical object. Including, the step of determining whether to predict the simulation computing load may determine whether to predict the simulation computing load based on a comparison result of the 1-1 physical data and the 1-2 physical data.

According to one embodiment, the step of determining whether to predict the simulation computing load includes the forest fire spread area at the immediately preceding time included in the 1-1 physical data and the most recent time included in the 1-2 physical data. It can be determined whether to predict the simulation computing load based on the difference in the forest fire spread area.

According to one embodiment, the simulation of the digital twin is a manufacturing process simulation, and the first physical data includes at least one information of the operating state, failure status, temperature, and power consumption of the equipment that is the physical object, and the simulation The step of determining whether to predict the computing load may determine whether to predict the simulation computing load based on a comparison result of the 1-1 physical data and the 1-2 physical data.

Specific details of other embodiments are included in the detailed description and drawings.

Figure 1 is a diagram for explaining a simulation device using distributed computing according to an embodiment of the present invention.
FIG. 2 is a diagram for explaining semantic data generated based on first and second physical data.
Figure 3 is a diagram for explaining the configuration of a distributed computing module according to an embodiment of the present invention.
Figure 4 is a diagram for explaining the configuration of a simulation control module according to an embodiment of the present invention.
Figure 5 is a diagram for explaining the configuration of a simulation performance module according to an embodiment of the present invention.
Figures 6 and 7 are diagrams for explaining a digital twin simulation method using distributed computing according to an embodiment of the present invention.

BRIEF DESCRIPTION OF THE DRAWINGS Various embodiments of the present invention are described below with reference to the accompanying drawings. However, this is not intended to limit the present invention to specific embodiments, but should be understood to include various modifications, equivalents, and/or alternatives to the embodiments of the present invention.

Due to the advancement of IT technology, the demand for digital twins, which provide simulations for analysis, prediction, and optimization of the status of specific physical objects or systems in a virtual environment, is increasing, and the development of corresponding technologies is also continuously advancing.

Digital twin-based simulation has developed to a level where accurate predictions can be made by utilizing formula-based models that simulate the state of physical objects and high-resolution sensor data, but simulation time increases due to the enormous amount of computing resources and the resulting increase in processing time. There is a problem.

To solve this problem, a method is being applied to support a rapid simulation process by dividing the required model into smaller sub-models, assigning each to multiple computing nodes, and processing them simultaneously. However, in the case of such distributed computing, the There is a limit to the latency of having to wait for the node with the longest computing time to terminate for state synchronization.

In order to overcome the above latency problem, a method of dividing the model has been developed considering the number or distribution of computing points where simulation operations occur, but it takes excessive time to predict the computing load (number of points, distribution, etc.). There is a problem in that the overall simulation time actually increases.

For example, in the case of forest fire prediction simulations, the ignition point of a forest fire is greatly influenced by geographical factors such as surrounding ignition fuel and terrain around the ignition point, and meteorological factors such as wind direction and precipitation, and the form of forest fire spread over time It changes. At this time, if a simulation is conducted considering only the number of ignition points of a forest fire, it is difficult to determine the computing load caused by surrounding factors that change the state of the forest fire over time, such as terrain and weather conditions.

Additionally, if partitioning is performed based on this, load imbalance may occur. For example, if there is a lot of dry grass, trees, etc. around one partitioned forest fire model through which fire can easily spread, the number of ignition points for a forest fire may increase over time, increasing the computing load. Conversely, if elements such as rocks that make it difficult to be certain about forest fires are mainly distributed around other forest fire model partitions, the spread of forest fires may become smaller over time, the number of ignition points may decrease, and the computing load may decrease. In this case, the degree of imbalance in the computing load between the two partitions may increase, and the delay time of each partition simulation may increase, making it difficult to respond quickly and appropriately to natural disasters.

Hereinafter, a digital twin simulation device and method using distributed computing according to some embodiments of the present invention will be described with reference to FIGS. 1 to 7.

FIG. 1 is a diagram for explaining a simulation device using distributed computing according to an embodiment of the present invention, and FIG. 2 is a diagram for explaining semantic data generated based on first and second physical data.

Referring to FIG. 1, the simulation device 10 according to an embodiment of the present invention transmits and receives data with the physical object 20, the database 30, and the visualization terminal 40, and thereby simulates the digital twin. can be performed.

The physical object 20 is a physical object corresponding to a digital twin, includes a plurality of sensors, and can transmit sensed data to the simulation device 10.

The database 30 stores static data of the physical object 20 and can transmit data necessary for simulation to the simulation device 10. For example, the database 30 may include terrain data such as altitude, slope direction, slope, and surrounding fuel model around the physical object 20. According to one embodiment, the database 30 is shown as being placed outside the simulation device 10, but this is an example and may be implemented to be physically/logically placed inside or outside the simulation device 10.

The visualization terminal 40 may output the status of the physical object 20 and simulation results received from the simulation device 10 in the form of visualization data. For example, the visualization terminal 40 may be implemented in the form of a smartphone, tablet PC, or server.

The simulation device 10 is a concept of a system organically combined with the physical object 20, and includes a simulation unit 200 to support rapid computing of the digital twin, acquiring and processing data for simulation of the digital twin, and It may include a data management unit 100 that provides.

Referring to FIGS. 1 and 2 , the data management unit 100 may include a semantic data generation module 110, an interface module 130, and a storage module 150. The interface module 130 may provide external or internal data transmission and reception. For example, first physical data DT1, which is real-time state data, is acquired from the physical object 20, second physical data DT2, which is static state data, is acquired from the database 30, and simulation result data DT_SIM ) can be provided as a visualization terminal (40).

The semantic data generation module 110 performs analysis on the first physical data DT1 and the second physical data DT2, and includes state information of the physical object 20 based on this, and the physical object 20 Semantic data (DT_SMT) for simulation can be generated.

The first physical data DT1 changes dynamically and may refer to data that can be collected in real time through the sensor of the physical object 20. For example, in the case of a forest fire prediction simulation, data such as surrounding temperature, humidity, precipitation, wind volume, wind speed, and the shape of the spread of the forest fire may be included in the first physical data DT1. As another example, in the case of manufacturing process simulation, data that can be measured in real time, such as the operating (failure) state of equipment, temperature, and power consumption, may be included in the first physical data DT1.

The second physical data DT2 may include static state information with little need for real-time collection. For example, in the case of a forest fire prediction simulation, data such as mountain altitude, slope, and fuel model may be included in the second physical data DT2. As another example, in the case of manufacturing process simulation, data such as manufacturing object, process sequence, number of times equipment is input, etc. may be included in the second physical data DT2.

In other words, it is difficult to determine the exact state of the physical object 20 with only single data, so analysis of semantic data (DT_SMT), which is multidimensional data, is required, and also static state data (second physical data (second physical data) that has little need for real-time collection) DT2)) can minimize the work load for data acquisition by storing it in the database 30 in advance.

As shown in FIG. 2 , a plurality of first physical data DT1 may be obtained from the physical object 20 and a plurality of second physical data DT2 may be obtained from the database 30 . The semantic data generation module 110 determines the data required for simulation of the digital twin among the plurality of first and second physical data (DT1 and DT2), extracts the necessary data, and generates semantic data (DT_SMT). .

FIG. 3 is a diagram for explaining the configuration of a distributed computing module according to an embodiment of the present invention, FIG. 4 is a diagram for explaining the configuration of a simulation control module according to an embodiment of the present invention, and FIG. 5 is a diagram for explaining the configuration of a distributed computing module according to an embodiment of the present invention. This is a diagram to explain the configuration of a simulation performance module according to an embodiment of the invention.

Referring to FIGS. 1 and 3 to 5, the simulation device 10 according to an embodiment of the present invention obtains semantic data (DT_SMT) from the data management unit 100, and simulates simulation result data based on this (DT_SMT). It may include a simulation unit 200 that provides DT_SIM). According to one embodiment, the simulation unit 200 may include a distributed computing module 210, a simulation control module 220, and a simulation performance module 230.

The distributed computing module 210 may include a load prediction determination module 211, a load prediction module 213, and a semantic data partitioning module 215.

The load prediction decision module 211 determines the load balancing process based on the degree of change in the state of the physical object 20 that may occur due to semantic data (DT_SMT) indicating the state of the physical object 20. At this time, the degree of change in the state of the physical object 20 may mean the degree of change in the size of the computing load due to the state of the physical object 20 in the previous step and the state of the physical object 20 in the current (next) step. . Information on changes in computing load size can be determined through analysis of semantic data (DT_SMT).

For example, in the case of a forest fire prediction simulation, if the semantic data (DT_SMT) contains a lot of information around the ignition point, such as a dry fuel model and strong winds that promote the spread of forest fires, the forest fire will increase over time and have a shape of spread compared to the initial state. will grow, which will increase the number of flash points and increase the computing load. Conversely, if the model includes fuel models such as rocks that are difficult for wildfires to spread and information about little wind blowing, the spread of wildfires may be reduced, and the computing load is likely to be reduced accordingly.

As another example, in the case of manufacturing process simulation, when various types of process modules are input, the manufacturing process may become large-scale and the computing load may increase. Conversely, for items that can be mass-produced, the manufacturing process can be scaled down and the computing load can be reduced because the changes in manufacturing semantic data are small.

When the change in state of the physical object 20 is small, the computing load is reduced, and thus the simulation time takes less. Therefore, when computing load prediction is performed, the total simulation time may increase due to the load prediction time. In other words, it may be more efficient to perform simulation without performing load prediction.

Conversely, when the state change of the physical object 20 is large, the overall simulation time is relatively long, so predict the computing load, reallocate the simulation session accordingly, and perform the simulation in the reallocated state to provide accurate and accurate results. Rapid simulation may be possible.

Accordingly, the simulation method and device according to an embodiment of the present invention analyzes semantic data (DT_SMT), and when it is determined that the change in the state of the physical object 20 is small, computing load prediction is omitted and partitioning, allocation and Accelerates the simulation of digital twins by performing distributed computing. Conversely, if the state change is judged to be large, the speed of simulation of the digital twin can be guaranteed by predicting the computing load and performing partitioning and computing by reflecting this.

If the degree of change is expected to be large according to the results of the load prediction determination module 211, the load prediction module 213 may predict the computing load through a machine learning model. That is, the computing load can be predicted based on semantic data (DT_SMT) and transmitted to the semantic data partitioning module 215.

The semantic data partitioning module 215 partitions the semantic data (DT_SMT) according to the results of the load prediction determination module 211. For example, in the case of forest fire prediction simulation, if the degree of change in the spread state of the forest fire, which is the physical object 20, is small, it means that the computing load, which is the simulation time, is small, and in this case, when performing distributed computing, the load imbalance occurs in the overall prediction time. It doesn't have much of an impact. Therefore, semantic data (DT_SMT) can be partitioned in a balanced manner. Conversely, if the degree of change in the forest fire spread state is large, the computing load, which is the simulation execution time, increases, and the load imbalance affects the overall prediction time, so after predicting the computing load, semantic data (DT_SMT) is balanced based on the prediction results. Partitioning.

The simulation control module 220 may include a simulation session control module 221 and a load balance control module 223.

According to one embodiment, the simulation session control module 221 acquires partitioned semantic data (DT_SMT), which is a simulation model (MD_SIM), configures distributed simulation sessions for seven days, and stores partitioned semantic data (DT_SMT) in each session. can be assigned. When the simulation for the allocated semantic data (DT_SMT) ends, the simulation control module 220 may end the simulation session. In addition, according to the load balance check result of the load balance control module 223, the simulation session is maintained or terminated to input the simulated semantic data into the simulation of the next time step.

According to one embodiment, the load balance control module 223 checks the load balance between each simulated semantic data (DT_SMT) every time a simulation step is performed, terminates the simulation if the load balance is greater than the standard, and semantics A reallocation command (SMD_RE) may be transmitted to the distributed computing module 210 to re-perform the data partitioning operation.

The simulation performance module 230, which is a logical node for performing multiple simulations, may include a plurality of simulation sessions 231 and a data bus 233 that provides data communication between components.

According to one embodiment, control messages between simulation control module 220, each simulation session 231, storage module 150, synchronization messages between each simulation session 231, and simulation results via data bus 233. Data (DT_SIM), etc. can be transmitted and received.

According to one embodiment, the simulation session 231 may include simulators capable of predicting the state of the physical object 20. Each simulation session 231 can transmit and receive synchronization messages through the data bus 233 for time synchronization, and transmit prediction results for each type step to the simulation control module 220 and the storage module 150.

Figures 6 and 7 are diagrams for explaining a digital twin simulation method using distributed computing according to an embodiment of the present invention.

Referring to FIG. 6, a digital twin simulation method using distributed computing according to some embodiments of the present invention includes the steps of acquiring first physical data including real-time state information of a physical object (S1000); Generating semantic data for the physical object based on the first physical data and pre-stored second physical data, which is static state information of the physical object (S3000); Analyzing the semantic data, partitioning it into at least one sub-semantic data, and allocating a simulation session corresponding to the sub-semantic data (S5000); And it may include performing a simulation on the digital twin of the physical object through the simulation session (S7000).

According to one embodiment, referring to FIG. 7, the step of allocating the simulation session (S5000) determines whether to predict the simulation computing load based on the state information of the physical object included in the semantic data (S5100). , When the load prediction is determined, it may include predicting the simulation computing load (S5300) and allocating the simulation session based on the simulation computing load prediction result (S5500).

The various embodiments of this document and the terms used herein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various changes, equivalents, or replacements of the embodiments. In connection with the description of the drawings, similar reference numbers may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the above items, unless the relevant context clearly indicates otherwise. In this document, “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C” and “A, Each of phrases such as “at least one of B, or C” may include any one of the items listed together in the corresponding phrase, or any possible combination thereof. Terms such as “first” and “second” may be used simply to distinguish one element from another and do not limit the elements in other respects (e.g., importance or order).

The term “module” used in this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit, for example. A module may be an integrated part or a minimum unit of the parts or a part thereof that performs one or more functions. For example, according to one embodiment, the module may be implemented in the form of an application-specific integrated circuit (ASIC).

Various embodiments of this document may be implemented as software including one or more instructions stored in a storage medium that can be read by a machine (eg, device 10). For example, a device (eg, device 10) may call at least one command among one or more commands stored from a storage medium and execute it. This allows the device to be operated to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. A storage medium that can be read by a device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain signals (e.g. electromagnetic waves), and this term refers to cases where data is semi-permanently stored in the storage medium. There is no distinction between temporary storage cases.

According to one embodiment, methods according to various embodiments disclosed in this document may be included and provided in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. A computer program product may be distributed in the form of a machine-readable storage medium (e.g. compact disc read only memory (CD-ROM)) or through an application store or between two user devices (e.g. smartphones). It may be distributed in person or online (e.g., downloaded or uploaded). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

According to various embodiments, each component (eg, module or program) of the above-described components may include a single entity or a plurality of entities. According to various embodiments, one or more of the components or operations described above may be omitted, or one or more other components or operations may be added. Alternatively or additionally, multiple components (eg, modules or programs) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each component of the plurality of components in the same or similar manner as those performed by the corresponding component of the plurality of components prior to the integration. . According to various embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or , or one or more other operations may be added.

10: Simulation device
20: Physics object
30: Database
40: Visualization terminal
100: Data management department
110: Semantic data generation module
130: interface module
150: storage module
200: Simulation unit
210: Distributed computing module
220: Simulation control module
230: Simulation performance module
231: Simulation session

Claims (10)

As a digital twin simulation method using distributed computing,
Obtaining first physical data including real-time state information of a physical object;
generating semantic data representing the state of the physical object based on pre-stored second physical data that is static state information of the physical object and the first physical data;
Analyzing the semantic data, partitioning the semantic data into at least one sub-semantic data, and allocating a simulation session corresponding to the sub-semantic data; and
Comprising the step of performing a simulation of a digital twin for the physical object through the simulation session,
Simulation methods for digital twins.
In claim 1,
The step of allocating the simulation session is,
Determine whether to predict simulation computing load based on state information of the physical object included in the semantic data,
predicting the simulation computing load when the load prediction is determined;
Allocating the simulation session based on simulation computing load prediction results,
Simulation methods for digital twins.
In claim 2,
The step of determining whether to predict the simulation computing load is,
Determining whether to predict the simulation computing load by analyzing real-time state information of the first physical data and static state information of the second physical data,
Simulation methods for digital twins.
In claim 3,
The simulation of the digital twin is a simulation of predicting the spread of forest fires,
The first physical data includes at least one of the surrounding temperature, humidity, precipitation, wind direction, wind speed, forest fire spread area, and ignition point of the physical object,
The second physical data includes at least one of the physical object's altitude, slope, slope direction, fuel model, and past forest fire state data,
The step of determining whether to predict the simulation computing load includes analyzing the first physical data and the second physical data to determine whether to predict the simulation computing load.
Simulation methods for digital twins.
In claim 3,
The simulation of the digital twin is a manufacturing process simulation,
The first physical data includes at least one of the operating status, failure status, temperature, and power consumption of the physical object, the equipment,
The second physical data includes at least one information among the manufacturing target of the physical object, manufacturing process sequence, and number of equipment inputs,
The step of determining whether to predict the simulation computing load includes analyzing the first physical data and the second physical data to determine whether to predict the simulation computing load.
Simulation methods for digital twins.
In claim 2,
The step of determining whether to predict the simulation computing load is,
The simulation computing based on a comparison result of 1-1 physical data including real-time state information of the physical object at the previous point in time and 1-2 physical data including real-time state information of the physical object at the most recent point in time. Determining whether to predict load,
Simulation methods for digital twins.
In claim 6,
The step of determining whether to predict the simulation computing load is,
If the difference between the 1-1 physical data and the 1-2 physical data is greater than or equal to a predefined reference difference, it is determined to perform the simulation computing load prediction, and if the difference is less than the reference difference, the simulation computing load prediction is not performed. Deciding to allocate the simulation session without
Simulation methods for digital twins.
In claim 6,
The simulation of the digital twin is a simulation of predicting the spread of forest fires,
The first physical data includes at least one of the surrounding temperature, humidity, precipitation, wind direction, wind speed, forest fire spread area, and ignition point of the physical object,
The step of determining whether to predict the simulation computing load includes determining whether to predict the simulation computing load based on a comparison result of the 1-1 physical data and the 1-2 physical data.
Simulation methods for digital twins.
In claim 8,
The step of determining whether to predict the simulation computing load is,
Determining whether to predict the simulation computing load based on the difference between the forest fire spread area at the previous point included in the 1-1 physical data and the forest fire spread area at the most recent point included in the 1-2 physical data,
Simulation methods for digital twins.
In claim 6,
The simulation of the digital twin is a manufacturing process simulation,
The first physical data includes at least one of the operating status, failure status, temperature, and power consumption of the physical object, the equipment,
The step of determining whether to predict the simulation computing load includes determining whether to predict the simulation computing load based on a comparison result of the 1-1 physical data and the 1-2 physical data.
Simulation methods for digital twins.